Applying machine learning models, a form of artificial intelligence (AI), to data passively collected from wearable devices can identify patient resilience and well-being, says Icahn School of Medicine, Mount Sinai, New York. researchers said.
The findings were reported on May 2nd.nd Problem of jamia open, Supports wearable devices such as Apple Watch®as a method of remotely monitoring and assessing psychological states without requiring completion of a mental health questionnaire.
The paper points out that resilience, or an individual’s ability to overcome adversity, is an important stress-reducing factor, reducing morbidity and improving management of chronic illness.
“Wearables offer a means of continuously collecting information about an individual’s physical state. Our results provide insight into the potential to assess psychological traits from this passively collected data.” Will” Digital Health of Mount Sinai. “To our knowledge, this is the first study to assess whether resilience, an important function of mental health, can be assessed from devices such as the Apple Watch.”
Mental health disorders are common, accounting for 13% of the global burden of illness, and a quarter of the population experience mental illness at some point. However, researchers say there are limited resources to evaluate them.
“There are large disparities in access by geography and socioeconomic status, further limiting the need for face-to-face assessments or completion of validated mental health surveys,” said senior author Zahi Fayyad, Ph.D. I’m here. At Icahn Mount Sinai. “We need a better understanding of who is at psychological risk and better means of tracking the impact of psychological interventions. The growth of digital technologies will improve access to mental health services for all.” It provides an opportunity to
To train a machine learning model to determine whether data from wearable devices can be used to distinguish between individual resilience and psychological well-being, researchers at Icahn Mount Sinai used data from the Warrior Watch Study. was analyzed. The dataset utilized for the current digital observational study consisted of his 329 health care workers enrolled at his seven hospitals in New York City.
Subjects wore Apple Watch® Series 4 or 5 during the participation period, and heart rate variability and resting heart rate were measured during the follow-up period. Surveys were collected to measure resilience, optimism, and emotional support at baseline. Collected metrics were found to be predictive in identifying resilience and health status. Although the Warrior Watch study was not designed to assess this endpoint, our findings support further evaluation of psychological properties from passively collected wearable data.
“We hope that this approach will enable us to provide psychological assessment and care to more people who may not have access to it at this time,” said co-author of the paper and associate director of clinical research at Hasso. said Micol Zweig of MPH. Plattner Digital Health Institute on Mount Sinai. “We also intend to evaluate this technique in other patient populations to further refine the algorithm and improve its applicability.”
To that end, the research team plans to use wearable data to continue observing various physical and psychological disorders and illnesses. The concurrent development of advanced analytical tools, including artificial intelligence, will make it easier to analyze the data collected from these devices and apps, allowing researchers to identify patterns associated with specific mental or physical disease states. said.
The title of this paper is “A Machine Learning Approach to Determining Resilience Using Wearable Device Data: An Observational Cohort Analysis.”
Other co-authors are Matteo Danielleto, PhD, Maria Suprun, PhD, Eddye Golden, MPH, Sparshdeep Kaur, BBA, Drew Helmus, MPH, Anthony Biello, BA, Dennis Charney, MD, Laurie Keefer, PhD, Mayte Suarez-Farinas , PhD, and Girish N Nadkami, MD from Icahn School of Medicine, Mount Sinai.
Support for this research was provided by the Ehrenkranz Lab for Human Resilience, BioMedical Engineering and Imaging Institute, Hasso Plattner Institute for Digital Health, Mount Sinai Clinical Intelligence Center, Dr. Henry D. Janowitz Division of Gastroenterology. Icahn Mount Sinai, and grant number K23DK129835 from the National Institutes of Health.
